Senior AI Engineer

Hub International Insurance•Chicago, IL

4d•Hybrid

About The Position

HUB International is seeking a Senior AI Engineer to serve as the most senior hands-on individual contributor in the AI Engineering function within its centralized technology organization. This individual contributor role has no direct reports, but carries technical authority and leads through standards, architecture, code review, and mentoring. The role establishes technical standards, owns technical decisions, resolves complex engineering problems, and is accountable for the reliability and governance of the function’s output—including standards applied to work by engineers outside the function. The role builds on HUB’s Claude AI platform by creating reusable skills and plug-ins, composing them into governed AI applications, developing retrieval over governed enterprise data, and turning experimental prototypes into tested, reliable, enterprise-ready applications. HUB currently uses Claude as its primary model and expects its stack to evolve toward agentic systems. Deep engineering work such as new backends, infrastructure, or complex integrations is executed by Enterprise Engineering to the standards this role defines, then returned to the catalog for governance and publication. The role does not build or host foundational models and does not perform core machine learning or model training. The Senior AI Engineer owns the technical operation of the skill and plug-in marketplace and MCP catalog, including intake, publishing, versioning, maintenance, deprecation, access control, and audit. The role also establishes evaluation, testing, monitoring, logging, governance, and production-support practices for AI assets and applications, while collaborating with business stakeholders and technical partners across HUB.

Requirements

At least 7 years of software or automation engineering experience, including at least 3 years building and shipping applications backed by large language models to production.
Direct, recent, hands-on experience building and publishing Claude skills or plug-ins; broad LLM or framework experience without shipped skills and plug-ins is insufficient.
Demonstrated technical leadership as an individual contributor, including setting standards followed by other engineers, reviewing architecture and code, and mentoring without managing.
Strong Python, REST API, and enterprise integration skills, with sound fundamentals in testing, version control, and monitoring.
Hands-on experience with foundational models, including system and prompt design, skill and tool building, and function and tool calling.
Experience with retrieval-augmented generation, embeddings, and vector stores, including chunking and reranking.
Experience with evaluation and monitoring for LLM-backed systems, and a working understanding of cost, latency, and reliability tradeoffs.
Experience working in a regulated enterprise where security, governance, and access control are part of normal delivery.
Cloud experience with Azure or GCP / Vertex AI.
Bachelor’s degree in Computer Science, Information Systems, Engineering, or a related technical field, or equivalent practical experience.
Genuine software engineering depth rather than prompt-only development.
Ability to influence without authority and set standards for engineers who do not report to the role.
Systems thinking and ability to design for consistency, resilience, and enterprise scale.
Willingness to handle documentation, evaluation harnesses, access reviews, and production support.
Coaching instinct and evidence of raising the level of other engineers.
Clear technical communication with engineers, business stakeholders, and executive audiences.
Accountability and ownership for quality, stability, governance, and delivery.
Curiosity and adaptability as the AI stack evolves toward agents.

Nice To Haves

Experience with agent development and orchestration, such as LangGraph, CrewAI, or Claude Agent SDK.
Model Context Protocol design, MCP server governance, and agent-to-agent patterns.
Knowledge of identity and access concepts, including RBAC, non-human or agent identity, and least privilege.
Working fluency in an AI governance framework such as the NIST AI Risk Management Framework, ISO/IEC 42001, or the NAIC model bulletin on insurer use of AI systems.
Experience as the senior technical voice in a new or maturing capability, including establishing standards where none existed.
UiPath or Microsoft Power Platform exposure.
Insurance or financial services industry experience and familiarity with audit and control expectations in a pre-IPO or public-company environment.
Familiarity with Git, CI/CD pipelines, modern software engineering practices, and tools such as Jira or Azure DevOps.

Responsibilities

Build reusable skills, package them as plug-ins, and compose them into governed AI applications used across HUB business lines.
Configure and tune foundational models for HUB use cases, including system and prompt design.
Build retrieval-augmented generation, embeddings, vector-store, and multi-step workflow implementations over governed enterprise data.
Productionize business-built AI prototypes into reliable, governed applications.
Own engineering decisions behind cost, latency, and reliability tradeoffs across the AI estate.
Define and document engineering standards for architecture patterns, testing, logging, documentation, and release discipline.
Review architecture and code across the team and improve the quality of delivered work.
Mentor AI Engineers and contract engineers, transferring knowledge to reduce dependence on any one person.
Set and uphold enterprise standards and governance for skills, plug-ins, and MCP across HUB, including work executed by other engineering teams.
Partner with Enterprise Engineering on deep builds and define the standards those builds must meet before returning to the catalog.
Own the technical operation of the skill and plug-in marketplace and MCP catalog, including intake, publishing, versioning, maintenance, and deprecation.
Apply access control, least privilege, and audit to AI assets in partnership with Security, Privacy, and Cloud teams on identity and credentials.
Ensure every AI asset published to the enterprise has a defined owner, documented behavior, and support path.
Establish and own evaluation harnesses, golden-set testing, guardrails, monitoring, and logging for consistent, reliable AI output at enterprise scale.
Establish acceptance criteria and regression gating to prevent changes from silently breaking other cases.
Provide production support and incident response for skills, plug-ins, and applications released by the function, including non-deterministic systems.
Translate governance, security, privacy, and regulatory requirements into engineering controls and audit-ready evidence.
Partner with business stakeholders and the product function to turn prototypes into production-ready, governed capabilities.
Partner with Enterprise Engineering, Data and Analytics, Cloud, and Security to deliver reliably and route deep builds appropriately.
Represent AI Engineering in technical and governance forums.
Participate in Agile ceremonies and document skills, applications, and technical decisions for handoff, audit, and maintenance.

Benefits

Competitive base salary plus performance-based bonus.
Comprehensive medical, dental, and vision coverage.
401(k) with company match.
Paid time off and company holidays.
Hybrid work arrangement based out of the Chicago office.
Professional development and certification reimbursement.
Structured training, licensing support, and ongoing development opportunities.
Retirement savings matching and company-paid life and disability plans.
Paid parental leave.
Wellbeing program designed to support work/life balance.
Potential eligible annual bonuses, equity, and commissions for some positions.
Collaborative culture, community impact through HUB Gives, and opportunities for career growth.